A focused catalogue of efficient open-weight models. Pricing is per 1M tokens. The machine-readable list is available from the models API.
qwen/qwen3.8-27b
Dense 27B vision-language model from Qwen's 3.8 family: 262K native context, optional thinking, and strong coding, agent, and multimodal performance.
google/gemma-4-e4b-it
Compact, efficient open model from Google's Gemma 4 family, served for fast, cost-efficient text generation with a 128K context window and native tool-use support.
Our models will be available through the OpenRouter marketplace.
We are actively expanding the catalogue. Models marked Available soon are launching on OpenRouter shortly. Need a specific open model? Let us know.